# On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems

arXiv: https://arxiv.org/abs/2509.25662 · HTML: https://mlsanity.com/paper/2509.25662/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [A Symbolic Approach to Explaining Bayesian Network Classifiers](https://mlsanity.com/paper/1805.03364/) (2018)
- [On The Reasons Behind Decisions](https://mlsanity.com/paper/2002.09284/) (2020)
- [Proxy Fairness](https://mlsanity.com/paper/1806.11212/) (2018)
- [Bias and Discrimination in AI: a cross-disciplinary perspective](https://mlsanity.com/paper/2008.07309/) (2020)
- [Eliminating The Impossible, Whatever Remains Must Be True](https://mlsanity.com/paper/2206.09551/) (2022)
- [Delivering Inflated Explanations](https://mlsanity.com/paper/2306.15272/) (2023)
- [Explainable Artificial Intelligence and Machine Learning: A reality rooted perspective](https://mlsanity.com/paper/2001.09464/) (2020)
- [What is Proxy Discrimination?](https://mlsanity.com/paper/2205.05265/) (2022)
- [Unlawful Proxy Discrimination: A Framework for Challenging Inherently Discriminatory Algorithms](https://mlsanity.com/paper/2404.14050/) (2024)
- [Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples](https://mlsanity.com/paper/2001.02271/) (2020)

## Built on by (most cited first, 1 of 1)

- [Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms](https://mlsanity.com/paper/2602.13985/) (2026)

## Abstract (arXiv)

Artificial intelligence (AI) systems in high-stakes domains raise concerns about proxy discrimination, unfairness, and explainability. Existing audits often fail to reveal why unfairness arises, particularly when rooted in structural bias. We propose a novel framework using formal abductive explanations to explain proxy discrimination in individual AI decisions. Leveraging background knowledge, our method identifies which features act as unjustified proxies for protected attributes, revealing hidden structural biases. Central to our approach is the concept of aptitude, a task-relevant property independent of group membership, with a mapping function aligning individuals of equivalent aptitude across groups to assess fairness substantively. As a proof of concept, we showcase the framework with examples taken from the German credit dataset, demonstrating its applicability in real-world cases.